Search papers, labs, and topics across Lattice.
8
0
10
11
Synthetic data that looks good can still tank your model's performance – Optimsyn uses influence functions to find the *actually* useful synthetic examples and optimize your generation rubrics.
Get clinically-accurate 3D dental models from a single panoramic X-ray, slashing radiation exposure and cost.
Vision-language models falter at the fine-grained temporal recognition crucial for surgical video understanding, while SurgRec excels.
LLM agents can achieve 3x faster web search and higher accuracy by dynamically routing between multiple context management strategies.
Forget real-world video datasets: training VLMs on just 7.7K synthetic videos with temporal primitives beats 165K real-world examples, unlocking surprisingly effective transfer learning for video reasoning.
Directly modeling 3D geometry in dental scans unlocks a 9.58% accuracy boost in multi-disease diagnosis compared to methods relying on 2D or multi-view image representations.
Group chats can be revitalized with LLM-powered agents, boosting message volume by nearly 30% in real-world deployments.
Current video benchmarks are too simple; UniVBench offers the first unified framework to measure the integrated capabilities of video foundation models using complex, multi-shot videos and a standardized evaluation system.
